netdev - Re: [PATCH net] net: let skb_orphan

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [day] [month] [year] [list]

Date:   Tue, 30 Mar 2021 17:32:09 +0200
From:   Eric Dumazet <edumazet@...gle.com>
To:     Paolo Abeni <pabeni@...hat.com>
Cc:     netdev <netdev@...r.kernel.org>
Subject: Re: [PATCH net] net: let skb_orphan_partial wake-up waiters.

On Tue, Mar 30, 2021 at 5:18 PM Paolo Abeni <pabeni@...hat.com> wrote:
>
> On Tue, 2021-03-30 at 16:40 +0200, Eric Dumazet wrote:

> > >
> > > Why TCP is not a problem here ?
>
> AFAICS, tcp_wfree() does not call sk->sk_write_space(). Processes
> waiting for wmem are woken by ack processing.

My concern was TCP Small Queue. If we do not call tcp_wfree() we might miss
an opportunity to queue more packets (and thus fallback to RTO or
incoming ACK is we are lucky)